# Novastart: up to 10 computer-use agents on a shared desktop canvas

**URL:** <https://forum.devtalk.com/t/novastart-up-to-10-computer-use-agents-on-a-shared-desktop-canvas/250837>\
**Category:** AI Libraries/Tools\
**Tags:** ai\
**Created:** [17 October 2026 05:11 UTC](https://forum.devtalk.com/t/novastart-up-to-10-computer-use-agents-on-a-shared-desktop-canvas/250837 "2026-10-17T05:11:39Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Novastart](https://forum.devtalk.com/user_avatar/forum.devtalk.com/novastart/32/8297_2.png) [@Novastart](https://forum.devtalk.com/u/Novastart)\
**Post date:** [17 October 2026 05:11 UTC](https://forum.devtalk.com/t/novastart-up-to-10-computer-use-agents-on-a-shared-desktop-canvas/250837/1 "2026-10-17T05:11:39Z")

</div>

Sharing a pattern from building Novastart ([https://novastart.com/](https://novastart.com/)), where up to 10 agents work on a desktop canvas, each with its own mouse and keyboard. A lead agent drafts a plan with one task per helper, and humans can pause or type a correction mid-run. The key piece is that “done means checked”: a separate check inspects a fresh screenshot before a task is marked complete, independent of the agent’s own report.

How are others structuring verification for computer-use agents: a separate check, a separate model, or human review?